save-fragment

save-fragment is a skill for Claude Code from serudda/fragments-vault. It costs 52 tokens per session (687 once invoked), scanned A, original, MIT.

A capture workflow for saving quotes, phrases, and ideas to an inbox while reading. It records the author and source, suggests tags, and asks why the item mattered to you.

In plain words
What is it for?
Use it to collect passages from books, websites, or other sources for later review and organisation.
Why use it?
It prevents useful fragments from being lost and avoids making you organise them fully while you are still reading.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Good fit Use it to collect passages from books, websites, or other sources for later review and organisation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/serudda/fragments-vault/save-fragment
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add serudda/fragments-vault --skill save-fragment
Clone the repo
git clone --depth 1 https://github.com/serudda/fragments-vault

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for save-fragment

README.md
[![agentmods](https://agentmods.dev/badge/skills/serudda/fragments-vault/save-fragment/github.svg)](https://agentmods.dev/skills/serudda/fragments-vault/save-fragment)
Your own site
<a href="https://agentmods.dev/skills/serudda/fragments-vault/save-fragment"><img src="https://agentmods.dev/badge/skills/serudda/fragments-vault/save-fragment/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for save-fragment

Your own site · 80×15
<a href="https://agentmods.dev/skills/serudda/fragments-vault/save-fragment"><img src="https://agentmods.dev/badge/skills/serudda/fragments-vault/save-fragment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 687 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00687
Opus 5 $0.00026 $0.00344
Sonnet 5 $0.00010 $0.00137
Haiku 4.5 $0.00005 $0.00069

Measured 10d ago against content hash d2c5ea7442bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

save-fragment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/save-fragment/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save Fragment

Role

You are a fragment capturer. Quickly save quotes, phrases, and ideas with zero friction.

Principles

  1. Speed matters - Capture fast, process later
  2. Tags from registry - Check existing tags first to avoid duplicates
  3. Why is gold - The reason it resonated is often more valuable than the quote
  4. Suggest, don't demand - Propose tags, let user confirm or adjust
  5. Date is automatic - Never ask for date, use today's date

Flow

Step 1: Receive the Fragment

User shares a quote, phrase, or idea.

Step 2: Ask for Author

Ask: "Who is the author? (name or 'unknown')"

Step 3: Ask for Source

Ask: "What is the source? (book, platform, URL, or 'unknown')"

Step 4: Show Tags & Suggest

  1. Read tags from CLAUDE.md
  2. Display them organized by category
  3. Suggest 2-4 tags based on the fragment content
  4. If a new tag is needed, propose it with "(new)" suffix
**Suggested tags**: #leverage #value #career

Do you want to add or change any?

If proposing new:

**Suggested tags**: #leverage #compound-growth (new)

The tag #compound-growth doesn't exist. Should we add it?

Step 5: Ask Why

Ask: "Why did it catch your attention?"

Encourage a real reason, not just "I liked it".

Step 6: Save to Inbox

Add to fragments/inbox.md using the format from CLAUDE.md.

Step 7: Update Tags Registry (if needed)

If new tags were approved, add them to the appropriate category in CLAUDE.md.

Step 8: Confirm

Saved to inbox. You have X pending fragments to process.

Quick Mode

If user provides everything in one message, skip redundant questions:

"Guarda: 'The quote here' - Author: Name, Source: Book/URL. Me resonó porque X."

→ Suggest tags, confirm, save.


Tag Management

Avoid Duplicates

Before creating a new tag, check if a similar one exists:

  • Want #career-growth? → Use #promotion or #skills
  • Want #maker? → Use #indie or #build-in-public

Read the full file on GitHub · 116 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 116 lines · 52 tokens per session scan A d2c5ea7442bb

Subscribe to this mod's changes

save-fragment is a skill published in the GitHub repository serudda/fragments-vault (6 stars, last pushed 7mo ago), licensed MIT. It adds 52 tokens to every session and 687 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

update-turbo

Update installed Turbo skills from the local repo with a dynamic changelog, conflict resolution for customized skills, and guided user experience. Use when the user asks to "update turbo", "update turbo skills", "reinstall turbo", or "upgrade turbo".

tobihagemann/turbo · 54 tokens

mm-resume

A workflow for restoring project context after starting a new Claude Code session or clearing the conversation. It reads project notes, recent session information, version-control status, and available planning files.

mworldorg/markdown-memory · 161 tokens

mm-setup

A setup guide that personalizes a shared mm system for one user. It asks for details such as your name, work area, tools, language, and Obsidian vault location, then saves them in private configuration files.

mworldorg/markdown-memory · 152 tokens

mm

A dispatcher that provides short /mm commands for project setup, session recovery, project overviews, and workflow checks. It maps these aliases to longer system commands.

mworldorg/markdown-memory · 103 tokens

file-organization

Use when organizing, deduplicating, or cleaning up files. Covers safe classification and renaming, finding true duplicates, reclaiming space, and never destroying data during a cleanup.

nimadorostkar/Claude-Skills-collection · 40 tokens

apple-shortcuts

Generate importable Apple Shortcuts (.shortcut / plist XML) for macOS and iOS. Use this skill whenever the user wants to create, modify, reverse-engineer, or understand Apple Shortcuts, including native actions, third-party app integrations (Actions, Data Jar, Toolbox Pro, Scriptable, a-Shell, Jayson, Pushcut)…

obeone/claude-skills · 133 tokens